Using Multispectral Drone Imaging to Monitor Soybean Cyst Nematode

Keywords: soybean cyst nematode (SCN), Multispectral, Drone Imaging
Session Type: Virtual Paper Abstract
Day: Friday
Session Start / End Time: 2/25/2022 02:00 PM (Eastern Time (US & Canada)) - 2/25/2022 03:20 PM (Eastern Time (US & Canada))
Room: Virtual 7

Abstract

The soybean cyst nematode (SCN) is responsible for losses amounting to 3 billion U.S dollars per annum incurred by soybean farmers in the U.S. The management options available for SCN such as resistant varieties, are challenged by the ever-adapting nature of SCN populations. The advances in remote sensing such as drone imaging and emerging technologies such as artificial intelligence provide an attractive alternative to conventional crop disease detection and monitoring methods. A drone and its onboard multispectral sensor allow flexible collection of field snapshots. The agricultural artificial intelligence (Agro-AI) models are especially suitable for identifying fuzzy-look features that are difficult to examine with regular field or image inspection. The purpose of this study is to develop a drone-based Agro-AI model to identify areas in soybean production fields with high nematode densities for more efficient management of SCN. The study area is a production soybean field located in Carmi, IL. The model was developed by combining SCN egg counts and the changes in color and texture that may be associated with pathogen-related crop stress. Preliminary results indicate drones and Agro-AI are suitable to be developed as a toolkit for monitoring SCN damage and population densities.